DOCSLIB.ORG

Report on Advances in the Field of Artificial Intelligence Attributed to Captcha

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Report on Advances in the Field of Artificial Intelligence Attributed to Captcha Utah State University DigitalCommons@USU All Graduate Plan B and other Reports Graduate Studies 12-2011 Report on Advances in the Field of Artificial Intelligence ttributedA to CAPTCHA Craig M. Schow Utah State University Follow this and additional works at: https://digitalcommons.usu.edu/gradreports Part of the Computer Sciences Commons Recommended Citation Schow, Craig M., "Report on Advances in the Field of Artificial Intelligence ttributedA to CAPTCHA" (2011). All Graduate Plan B and other Reports. 69. https://digitalcommons.usu.edu/gradreports/69 This Report is brought to you for free and open access by the Graduate Studies at DigitalCommons@USU. It has been accepted for inclusion in All Graduate Plan B and other Reports by an authorized administrator of DigitalCommons@USU. For more information, please contact [email protected]. i REPORT ON ADVANCES IN THE FIELD OF ARTIFICIAL INTELLIGENCE ATTRIBUTED TO CAPTCHA By Craig M. Schow A report submitted in partial fulfillment of the requirements for the degree of MASTERS OF SCIENCE in Computer Science Approved: ____________________ ____________________ Dr. Donald Cooley Dr. Stephen Clyde Major Professor Committee Member ____________________ Dr. Nicholas Flann Committee Member UTAH STATE UNIVERSITY Logan, Utah 2011 ii ABSTRACT Report on Advances in the Field of Artificial Intelligence Attributed to CAPTCHA by Craig M. Schow, Master of Science Utah State University, 2011 Major Professor: Dr. Donald Cooley Department: Computer Science A CAPTCHA is a specialized human interaction proof that exploits gaps between human and computer recognition abilities. By design, the hardness of a CAPTCHA is based on the difficulty of advancing the underlying artificial intelligence [AI] technology to a level that eliminates any exploitable gap. Due to this fact computer scientists have concluded that the widespread use of CAPTCHA would accelerate research in the underlying fields of AI eventually leading to near-human capabilities in certain AI systems. Despite these predictions no attempt has been made to identify advances in AI which can be attributed to the use of CAPTCHA. The goal of this report is to explore the concept of CAPTCHA as a catalyst for advancement in AI. As part of this goal I examine the underlying basis for expected contributions, provide direct examples of documented advancements that have already been made, evaluate the strengths and weaknesses of the CAPTCHA model and based on the results identify specific areas of AI most likely to benefit from CAPTCHA in the future. As a result of my research I have found that some advancement has been made as a result of CAPTCHA, but due to weaknesses in many CAPTCHA implementations these advancements have been limited and have often fallen short of expectations. As many of these weaknesses have been identified new methods of implementation have been introduced, but many of these have limitations as well. As part of the exploration of these challenges I have provided a basis that will allow for a more accurate understanding of the processes involved, and allow others to continue to build on the work which has already been done. iii CONTENTS ABSTRACT ........................................................................................................................................ii CHAPTER I. INTRODUCTION ............................................................................................................1 II. OVERVIEW OF CAPTCHA ..............................................................................................3 CAPTCHA................................................................................................................3 How CAPTCHA Works ............................................................................................3 Gap Amplification ..................................................................................................8 Uses of CAPTCHA ...................................................................................................8 III. BASIS OF CAPTCHA AS A CATALYST............................................................................10 CAPTCHA as a Catalyst.........................................................................................10 Precisely Stating the Problem..............................................................................10 Inducing Research................................................................................................11 IV. DIRECT EXAMPLES......................................................................................................13 Mori and Malik ....................................................................................................13 V. OPOSSING VIEWS .......................................................................................................16 Human Tolerance and Accessibility .....................................................................16 Specialization of Recognizers...............................................................................16 Useless Answers ..................................................................................................17 VI. ONGOING AND FUTURE IMPROVEMENTS .................................................................18 The Strengths of CAPTCHA ..................................................................................18 Real Pattern Recognition .....................................................................................18 Human Cognitive Sciences...................................................................................20 Linguistic Cognition..............................................................................................21 VII. CONCLUSION..............................................................................................................23 BIBLIOGRAPHY...............................................................................................................................25 1 CHAPTER 1 INTRODUCTION A CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) is a type of challenge-response authentication that exploits gaps between human and computer recognition abilities in order to determine if the user is human. By design, the hardness of a CAPTCHA is based on the difficulty of advancing the underlying artificial intelligence [AI] technology to a level that eliminates any exploitable gap. This type of system is similar to some forms of public key cryptography where the underlying hardness is based on the difficulty of factoring large numbers. Thus, if an attacker can solve the underlying problem they will be able to defeat the protocol. Due to this fact, many computer scientists have concluded that the widespread use of CAPTCHA would accelerate research in the underlying field of AI eventually leading to near-human capabilities in certain AI systems much like cryptography has motivated research on algorithms and hardware used for factoring [1, 2, 3, 4, 5, 17]. Despite the common acceptance of CAPTCHA as a catalyst for advancing research in some fields of AI, very little work has been done to check the validity of this assumption or identify weaknesses that could be addressed. This report is intended to fill in the knowledge gap between the expectations that have been expressed and the actual results that have been produced. I have divided this report into the following chapters: Overview of CAPTCHA In this chapter I detail the main uses of CAPTCHA, describe how it works, and introduce any terms that are relevant to the report. This chapter contains enough detail to allow an individual who is unfamiliar with CAPTCHA to follow the ideas expressed in other sections of the report. Basis of CAPTCHA as a Catalyst In this chapter I explore the initial reasoning behind the idea that CAPTCHA would have a positive effect on the field of AI. I provide examples of related problems on which this reasoning is based and draw conclusions concerning expected outcomes. I also detail any underlying assumptions which have been made. Direct Examples In this chapter I identify specific examples of recent advancements in the field of AI that can be attributed in part to the use of CAPTCHA. Based on my findings, I identify strengths that have lead to success and areas in which advancements have fallen short of expectations. Opposing Views 2 In this chapter I explore many of the weaknesses that have been identified in current implementations of CAPTCHA. As weaknesses are presented I identify how each limits the potential effectiveness of CAPTCHA in advancing AI. Future Improvements In this chapter I take what has been learned and project that knowledge forward in an attempt to outline future contributions that could be made. I identify specific areas for improvement and outline areas of AI most likely to be impacted. Finally, I identify a general framework that can be applied to future problems 3 CHAPTER 2 OVERVIEW OF CAPTCHA CAPTCHA A CAPTCHA is a type of challenge-response authentication schema that asks “Are you human?” [2] The term CAPTCHA stands for “Completely Automated Public Turing Test to Tell Computers and Humans Apart” [7]. Many authors refer to CAPTCHAs as a type of Human Interactive Proof (HIP). In order to differentiate between a human and a computer the CAPTCHA program generates a test that is easily solved by humans, but difficult to solve using a computer [1]. Generally these tests take the form of distorted text, images or audio and are often found
Load more

Recommended publications
  • Recaptcha: Human-Based Character Recognition Via Web Security
    REPORTS on September 12, 2008 and blogs. For example, CAPTCHAs prevent www.sciencemag.org reCAPTCHA: Human-Based Character ticket scalpers from using computer programs to buy large numbers of concert tickets, only to re Recognition via Web Security Measures sell them at an inflated price. Sites such as Gmail and Yahoo Mail use CAPTCHAs to stop spam Luis von Ahn,* Benjamin Maurer, Colin McMillen, David Abraham, Manuel Blum mers from obtaining millions of free e mail accounts, which they would use to send spam CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) are e mail. Downloaded from widespread security measures on the World Wide Web that prevent automated programs from According to our estimates, humans around abusing online services. They do so by asking humans to perform a task that computers cannot yet the world type more than 100 million CAPTCHAs perform, such as deciphering distorted characters. Our research explored whether such human every day (see supporting online text), in each case effort can be channeled into a useful purpose: helping to digitize old printed material by asking spending a few seconds typing the distorted char users to decipher scanned words from books that computerized optical character recognition failed acters. In aggregate, this amounts to hundreds of to recognize. We showed that this method can transcribe text with a word accuracy exceeding 99%, thousands of human hours per day. We report on matching the guarantee of professional human transcribers. Our apparatus is deployed in more an experiment that attempts to make positive use than 40,000 Web sites and has transcribed over 440 million words.
    [Show full text]
  • Are Captchas Preventing Robotic Intrusion Or Accessibility for Impaired Users?
    2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC) Are CAPTCHAs preventing robotic intrusion or accessibility for impaired users? Rudy Berton1, Ombretta Gaggi1, Agnieszka Kolasinska2, Claudio Enrico Palazzi1, Giacomo Quadrio1 1Department of Mathematics “Tullio Levi-Civita” 2Department of General Psychology University of Padua Padua, Italy fgaggi, cpalazzi, [email protected], [email protected] Abstract—Is the World Wide Web for everyone? Long story Moreover, CAPTCHAs often use the English language, thus short: no and unfortunately it is not only a matter of infrastruc- excluding the non-English speaking web users in the world. tures, level of instruction or economic conditions. People affected In this paper, we present an overview of CAPTCHA’s by visual impairments have often difficulties in navigating web pages for a wide range of reasons. One of the biggest obstacles current technologies and data collected during an experiment nowadays is the use of CAPTCHAs, powerful tools against bot involving both regular users and visually impaired ones nav- attacks but also potential virtual barriers for the aforementioned igating the web with the aid of a screen reader. We asked category of users. In this paper we tested various categories of participants to answer to a questionnaire organized in ten CAPTCHAs with people affected by visual impairment and not, pages, each of which contained a CAPTCHA. Different types to understand how discriminatory can be these cybersecurity measures. of CAPTCHA have been used and we collected data about Index Terms—accessibility, CAPTCHA, visual impairment users’ answers, mouse’s movements and interactions, as well as data about the success or failure of the CAPTCHAs.
    [Show full text]
  • Research on the Security of Visual Reasoning CAPTCHA
    Research on the Security of Visual Reasoning CAPTCHA Yipeng Gao1, Haichang Gao1*, Sainan Luo1, Yang Zi1, Shudong Zhang1, Wenjie Mao1, Ping Wang1, Yulong Shen1 and Jeff Yan2 1School of Computer Science and Technology, Xidian University 2Department of Computer and Information Science, Linkoping¨ University Abstract Text-based CAPTCHAs have long been the most widely CAPTCHA is an effective mechanism for protecting comput- used scheme because of their simple structure and low cost. ers from malicious bots. With the development of deep learn- Such a CAPTCHA relies on a text recognition problem to ing techniques, current mainstream text-based CAPTCHAs distinguish humans from computers [51]. To resist the attack, have been proven to be insecure. Therefore, a major effort has text-based CAPTCHAs are often specifically designed with been directed toward developing image-based CAPTCHAs, anti-segmentation features and anti-recognition features [6]. and image-based visual reasoning is emerging as a new di- However, with advances in segmentation and character recog- rection of such development. Recently, Tencent deployed nition technologies, most text-based CAPTCHAs have been the Visual Turing Test (VTT) CAPTCHA. This appears to solved [15], [5], [45], [32], [55], [14], [56], [13], [4], [57], have been the first application of a visual reasoning scheme. [60], and designers need to find a new way to achieve se- Subsequently, other CAPTCHA service providers (Geetest, curity. Subsequently, image-based CAPTCHAs have been NetEase, Dingxiang, etc.) have proposed their own visual proposed. The image-based scheme is more diverse in con- reasoning schemes to defend against bots. It is, therefore, tent and background, and thus, it seems to be more secure than natural to ask a fundamental question: are visual reason- the text-based scheme.
    [Show full text]
  • A Survey on Breaking Technique of Text-Based CAPTCHA
    Hindawi Security and Communication Networks Volume 2017, Article ID 6898617, 15 pages https://doi.org/10.1155/2017/6898617 Review Article A Survey on Breaking Technique of Text-Based CAPTCHA Jun Chen,1,2 Xiangyang Luo,1 Yanqing Guo,3 Yi Zhang,1 and Daofu Gong1 1 State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450002, China 2Henan Institute of Science and Technology, Xinxiang 453003, China 3Dalian University of Technology, Dalian 116024, China Correspondence should be addressed to Xiangyang Luo; luoxy [email protected] Received 25 September 2017; Accepted 27 November 2017; Published 24 December 2017 Academic Editor: Zhenxing Qian Copyright © 2017 Jun Chen et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The CAPTCHA has become an important issue in multimedia security. Aimed at a commonly used text-based CAPTCHA, this paper outlines some typical methods and summarizes the technological progress in text-based CAPTCHA breaking. First, the paper presents a comprehensive review of recent developments in the text-based CAPTCHA breaking field. Second, a framework of text-based CAPTCHA breaking technique is proposed. And the framework mainly consists of preprocessing, segmentation, combination, recognition, postprocessing, and other modules. Third, the research progress of the technique involved in each module is introduced, and some typical methods
    [Show full text]
  • Luis Von Ahn - Episode 14 Transcript
    ACM ByteCast Luis von Ahn - Episode 14 Transcript Rashmi Mohan: This is ACM ByteCast, a podcast series from the Association for Computing Machinery, the world's largest educational and scientific computing society. We talk to researchers, practitioners, and innovators who are at the intersection of computing research and practice. They share their experiences, the lessons they've learned, and their own visions for the future of computing. I am your host, Rashmi Mohan. Rashmi Mohan: If you want to boost your brain power, improve your memory, or enhance your multitasking skills, then you're often recommended to learn a foreign language. For many of us, that option has become a reality, thanks to our next guest and his creation. Luis von Ahn is a serial entrepreneur and Founder and CEO of Duolingo. An accomplished researcher and consulting professor of Computer Science at Carnegie Mellon University, he straddles both worlds seamlessly. He's a winner of numerous awards, including the prestigious Lemelson-MIT Prize and the MacArthur Fellowship often known as The Genius Grant. Louis, welcome to ACM ByteCast. Luis von Ahn: Thank you. Thank you for having me. Rashmi Mohan: Wonderful. I'd love to lead with a simple question that I ask all of my guests. If you could please introduce yourself and talk about what you currently do, and also give us some insight into what drew you into the field of computer science. Luis von Ahn: Sure. So my name is Luis. I am currently the CEO and co-founder of a company called Duolingo. Duolingo is a language learning platform.
    [Show full text]
  • I Am Not a Robot: an Overview on Google's Captcha
    I AM NOT A ROBOT: - AN OVERVIEW ON GOOGLE’S CAPTCHA A Thesis Presented to the Faculty of California State Polytechnic University, Pomona In Partial Fulfillment Of the Requirements for the Degree Master of Science In Computer Science By Uday Prabhala 2016 SIGNATURE PAGE THESIS: I AM NOT A ROBOT: - AN OVERVIEW ON GOOGLE’S CAPTCHA AUTHOR: Uday Prabhala DATE SUBMITTED: Summer 2016 Computer Science Department. Dr. Gilbert Young ___________________________________________ Thesis Committee Chair Computer Science Dr. Fang D. Tang ___________________________________________ Computer Science Dr. Yu Sun ___________________________________________ Computer Science ii ACKNOWLEDGEMENTS I would like to express my deepest gratitude to my family members, Yashoda, Lucky, and Diskey, as well as my girlfriend Siri, who helped make this endeavor possible. Their limitless support, assistance, and encouragement during the times when I was close to giving up were greatly helpful, and I wouldn’t have been able to overcome the obstacles without them. I would also like to send my appreciation and gratitude to the Professors who were part of my thesis committee. Most notably, I would like to thank Professor Gilbert Young, chair of the committee, for his support, patience, guidance, and sharing of knowledge throughout the program. I would also like to thank Professor Tang and Professor Yusun for reviewing my paper and attending my presentation. The above three Professors not only helped me to complete my program, but also served as an excellent example by exercising professionalism, versatility, and commitment to the developing engineering students at California State Polytechnic University, Pomona. iii ABSTRACT I am not a Robot Overview on Google’s Captcha Uday Kiran Prabhala Computers are one of the greatest inventions done by humans; these devices not only made our work easy, but could also be misused in various ways.
    [Show full text]
  • Fedramp Master Acronym and Glossary Document
    FedRAMP Master Acronym and Glossary Version 1.6 07/23/2020 i​[email protected] fedramp.gov Master Acronyms and Glossary DOCUMENT REVISION HISTORY Date Version Page(s) Description Author 09/10/2015 1.0 All Initial issue FedRAMP PMO 04/06/2016 1.1 All Addressed minor corrections FedRAMP PMO throughout document 08/30/2016 1.2 All Added Glossary and additional FedRAMP PMO acronyms from all FedRAMP templates and documents 04/06/2017 1.2 Cover Updated FedRAMP logo FedRAMP PMO 11/10/2017 1.3 All Addressed minor corrections FedRAMP PMO throughout document 11/20/2017 1.4 All Updated to latest FedRAMP FedRAMP PMO template format 07/01/2019 1.5 All Updated Glossary and Acronyms FedRAMP PMO list to reflect current FedRAMP template and document terminology 07/01/2020 1.6 All Updated to align with terminology FedRAMP PMO found in current FedRAMP templates and documents fedramp.gov page 1 Master Acronyms and Glossary TABLE OF CONTENTS About This Document 1 Who Should Use This Document 1 How To Contact Us 1 Acronyms 1 Glossary 15 fedramp.gov page 2 Master Acronyms and Glossary About This Document This document provides a list of acronyms used in FedRAMP documents and templates, as well as a glossary. There is nothing to fill out in this document. Who Should Use This Document This document is intended to be used by individuals who use FedRAMP documents and templates. How To Contact Us Questions about FedRAMP, or this document, should be directed to ​[email protected]​. For more information about FedRAMP, visit the website at ​https://www.fedramp.gov​.
    [Show full text]
  • An Object Detection Based Solver for Google's Image Recaptcha V2
    An Object Detection based Solver for Google’s Image reCAPTCHA v2 Md Imran Hossen∗ Yazhou Tu∗ Md Fazle Rabby∗ Md Nazmul Islam∗ Hui Cao† Xiali Hei∗ ∗University of Louisiana at Lafayette †Xi’an Jiaotong University Abstract have emerged as a superior alternative to text ones as they are considered more robust to automated attacks. Previous work showed that reCAPTCHA v2’s image chal- lenges could be solved by automated programs armed with reCAPTCHA v2, a dominant image CAPTCHA service Deep Neural Network (DNN) image classifiers and vision released by Google in 2014, asks users to perform an im- APIs provided by off-the-shelf image recognition services. age recognition task to verify that they are humans and not In response to emerging threats, Google has made signifi- bots. However, in recent years, deep learning (DL) algorithms cant updates to its image reCAPTCHA v2 challenges that have achieved impressive successes in several complex image can render the prior approaches ineffective to a great extent. recognition tasks, often matching or even outperforming the In this paper, we investigate the robustness of the latest ver- cognitive ability of humans [30]. Consequently, successful sion of reCAPTCHA v2 against advanced object detection attacks against reCAPTCHA v2 that leverage Deep Neural based solvers. We propose a fully automated object detection Network (DNN) image classifier and off-the-shelf (OTS) im- based system that breaks the most advanced challenges of age recognition services have been proposed [44, 50]. reCAPTCHA v2 with an online success rate of 83.25%, the The prior work advanced our understanding of the security highest success rate to date, and it takes only 19.93 seconds issues of image CAPTCHAs and led to better CAPTCHA (including network delays) on average to crack a challenge.
    [Show full text]
  • Simple Text Based Captcha for the Security in Web Applications
    Vidya P N et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.4, April- 2015, pg. 519-531 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IJCSMC, Vol. 4, Issue. 4, April 2015, pg.519 – 531 RESEARCH ARTICLE SIMPLE TEXT BASED CAPTCHA FOR THE SECURITY IN WEB APPLICATIONS Vidya P N, Dr. Shrinivasa Naika C.L Computer Science and Engineering Department, U.B.D.T College of Engineering, Davanagere, Karnataka, India ABSTRACT CAPTCHA is an acronym for Completely Automated Public Turing test to tell Computers and Humans apart. CAPTCHA systems are used as a security mechanism in web applications. Text-Based CAPTCHA is the most widely used CAPTCHA. Due to the wide popularity the text-based CAPTCHAs are more vulnerable to attacks. Hence there is an immense need to improve the strength of the text-based CAPTCHA to hinder many of such breaking attacks. This paper proposes a simple text based CAPTCHA approach that thwarts many of the breaking attacks and provides reliable and usable way to distinguish between humans and computers. CHAPTER 1 INTRODUCTION Presently, living has changed the dimension with the introduction of the Internet to mankind, ways people connect to each other, advertising, shopping, education, etc. Consequently, system security has become the most important issue for any websites since there © 2015, IJCSMC All Rights Reserved 519 Vidya P N et al, International Journal of Computer Science and Mobile Computing, Vol.4 Issue.4, April- 2015, pg.
    [Show full text]
  • Making Captchas Clickable
    Making CAPTCHAs Clickable Richard Chow Philippe Golle Markus Jakobsson Palo Alto Research Center Palo Alto Research Center Palo Alto Research Center [email protected] [email protected] [email protected] Lusha Wang Xiaofeng Wang Indiana University at Indiana University at Bloomington Bloomington [email protected] [email protected] ABSTRACT in automated techniques for solving CAPTCHAs have ne- We show how to convert regular keyboard-entry CAPTCHAs cessitated the development of ever harder CAPTCHAs to into clickable CAPTCHAs. The goal of this conversion is elude attackers. CAPTCHAs have become sufficiently hard to simplify and speed-up the entry of the CAPTCHA so- for humans to solve that many service providers now balk lution, to minimize user frustration and permit the use of at deploying them for fear of deterring potential clients. CAPTCHAs on devices where they would otherwise be un- suitable. We propose a technique for producing secure click- For users of handheld computers, the problem is compounded able CAPTCHAs that are well suited for use on cell phones by the fact that entering the CAPTCHA solution on a mo- and other mobile devices. We support the practical viability bile device is more cumbersome and time-consuming than on of our approach by results from a user study, and an analysis a traditional keyboard. Given that close to 40% of all adults of its security guarantees. in Japan browse the Internet from a mobile device [9], this is a significant problem | at least in Japan, and increasingly Categories and Subject Descriptors elsewhere too. A test to distinguish humans from computers K.6.5 [Computing Milieux]: Management of Computing that can be solved only with clicks of a mouse or stylus would and Information Systems|Security and Protection be far less distracting and more acceptable to most users, particularly mobile users|provided the number of clicks is relatively small, and the cognitive task within reason.
    [Show full text]
  • CAPTCHA Sushma Yalamanchili 1 and Kameswara Rao 2
    A FRAMEWORK FOR DEVA NAGARI SCRIPT -BASED CAPTCHA Sushma Yalamanchili 1 and Kameswara Rao 2 1Research Scholar, Department of Computer Science & Engineering Acharya Nagarjuna University, Andhra Pradesh, India. [email protected] 2Department of Computer Science, P.G.Centre, P.B.Siddhartha College, Vijayawada. [email protected] ABSTRACT Human Interactive Proofs (HIPs) are automatic reverse Turing tests designed to distinguish between various groups of users. Completely Automatic Public Turing test to tell Computers and Humans Apart (CAPTCHA) is a HIP system that distinguish between humans and malicious computer programs. Many CAPTCHAs have been proposed in the literature that text-graphical based, audio-based, puzzle-based and mathematical questions-based. The design and implementation of CAPTCHAs fall in the realm of Artificial Intelligence. We aim to utilize CAPTCHAs as a tool to improve the security of Internet based applications. In this paper we present a framework for a text-based CAPTCHA based on Devanagari script which can exploit the difference in the reading proficiency between humans and computer programs. Our selection of Devanagari script-based CAPTCHA is based on the fact that it is used by a large number of Indian languages including Hindi which is the third most spoken language. There is potential for an exponential rise in the applications that are likely to be developed in that script thereby making it easy to secure Indian language based applications. KEYWORDS CAPTCHA, Devanagari, Human Interactive Proof, Optical Character Recognition, text-based. 1. INTRODUCTION Human Interactive Proofs (HIPs) [1] focus on automation tests that virtually all humans can pass but current computer programs fail [2].
    [Show full text]
  • Captcha for Visually Impaired People: a Review
    International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 08 Issue: 05 | May 2021 www.irjet.net p-ISSN: 2395-0072 Captcha for Visually Impaired People: A Review Sakshi Baheti1, Hardik Shah1, Rijul Sherathia1, Prakash Waghamode2 1Student, 2Professor, School of Computer Engineering and Technology, MIT World Peace University Kothrud, Pune 411038 ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Nowadays the Internet users are from different groups are using the Internet. There are many websites for ages and groups. The disabled people also use the Internet. children on the Internet and the children using the Internet Some websites are especially created for disabled people. Many for various activities such as entertaining, educating, etc. The Internet sites offer services for human users, but unfortunately elderly people communicate and chat with their children and some computer programs are designed which abuse these relatives using the Internet. In addition to regular people, the services. As a result, some systems named CAPTCHA disabled peoples are also using the Internet. Deploying only (Completely Automated Public Turing test to tell Computers visual captchas creates a considerable obstacle to a certain and Human Apart) [3] have been introduced to tell apart group of users, such as the visually impaired, colour-blind, human users and computer software. In this paper, a new near sighted users. This necessitates the need for more CAPTCHA method is introduced which blind people can use. In accessible captchas. this method, a simple shape-based problem is created according to predefined patterns and converted to speech Current CAPTCHAs rely on superior human perception, using a Text-To-Speech (TTS) system.
    [Show full text]